Coding & Development

game-datasets is a comprehensive GitHub repository offering a curated list of awesome game datasets and tools specifically designed for artificial intelligence in games. This resource is invaluable for researchers, developers, and enthusiasts working on AI or data mining applications within the digital games domain. The repository categorizes its offerings into APIs for accessing game data, various AI experimentation platforms and competitions, mobile game resources, relevant books, and an extensive collection of game datasets. These datasets cover a wide range of games, from popular titles like League of Legends and Dota 2 to classic board games and even Pokémon. Additionally, it includes related datasets, market research, and miscellaneous resources, making it a central hub for anyone looking to build AI applications or conduct data analysis in gaming.

Gemma is an open-weight Large Language Model (LLM) library developed by Google DeepMind, leveraging research and technology from the Gemini models. This repository offers the implementation of the gemma PyPI package, providing a JAX library for both using and fine-tuning Gemma models. It supports multi-turn, multi-modal conversations and offers various versions of Gemma. The library is designed to run on CPU, GPU, and TPU, with specific RAM recommendations for GPU usage (8GB+ for 2B checkpoint, 24GB+ for 7B checkpoint). Extensive documentation, Colabs, and tutorials are available for sampling, multi-modal fine-tuning, and LoRA.

FunASR is a fundamental end-to-end speech recognition toolkit designed to bridge the gap between academic research and industrial applications. It offers a comprehensive suite of features including speech recognition (ASR), Voice Activity Detection (VAD), Punctuation Restoration, Language Models, Speaker Verification, Speaker Diarization, and multi-talker ASR. The toolkit provides convenient scripts and tutorials for both inference and fine-tuning of pre-trained models. FunASR boasts a vast collection of academic and industrial pre-trained models available on ModelScope and Hugging Face, including the highly accurate and efficient Paraformer-large. Recent updates include support for large models like Fun-ASR-Nano-2512 (31 languages), Whisper-large-v3-turbo, and Qwen-Audio multimodal models, alongside continuous improvements in real-time and offline transcription services, memory optimization, and multi-platform support.

free-llm-api-resources is a comprehensive list of services that provide free access or trial credits for API-based Large Language Model (LLM) usage. This resource is invaluable for developers, researchers, and students looking to experiment with LLMs without initial financial commitment. The list details various providers like OpenRouter, Google AI Studio, NVIDIA NIM, Mistral, HuggingFace, and others, specifying their free tiers, usage limits, and available models. It also includes providers offering trial credits such as Fireworks, Baseten, and AI21. The tool emphasizes legitimate services, explicitly excluding those that reverse-engineer existing chatbots, ensuring users find reliable and ethical resources for their projects.

generative-ai-go is a Go SDK developed by Google for integrating their Generative AI models, including Gemini, Veo, and Imagen, into Go applications. This SDK was created to offer a unified and streamlined interface for developers to leverage Google's powerful generative AI capabilities within the Go programming language ecosystem. While this specific repository is now considered legacy and is in limited maintenance for critical bug fixes only, it served as an important step in providing Go developers access to these advanced models. Users are strongly encouraged to migrate to the official Google Generative AI SDK for Go for the latest features, performance improvements, and active development, as support for this repository will permanently end on November 30, 2025.

PromptWizard is an open-source, task-aware, agent-driven framework designed for optimizing prompts used with Large Language Models (LLMs). It features a self-evolving mechanism where the LLM itself generates, critiques, and refines its own prompts and in-context learning examples. This iterative feedback loop ensures continuous improvement in task performance. The framework focuses on holistic optimization by evolving both instructions and examples, generating synthetic, diverse, and task-aware examples. It also supports self-generated Chain of Thought (CoT) steps and offers various scenarios for prompt optimization, including with and without training data, and the generation of synthetic examples. Users can configure hyperparameters and integrate with custom datasets, making it a flexible tool for developers and researchers working with LLMs.

Midjourney Prompts Generator is an AI tool designed to assist users in creating compelling and varied prompts specifically for AI art generation platforms like Midjourney. It aims to alleviate creative blocks by offering a wide array of styles, themes, and conceptual suggestions. The generator simplifies the ideation phase, enabling creators to efficiently produce distinctive visual content. By providing a structured approach to prompt creation, it helps users explore new artistic directions and achieve more precise and imaginative results from their AI art models. This tool is particularly useful for those looking to enhance their AI art workflow and generate unique outputs.

PointNet is a novel deep learning architecture specifically designed for processing point clouds, which are an important type of geometric data structure. Unlike traditional methods that convert point clouds into regular 3D voxel grids or image collections, PointNet directly consumes unordered point sets, respecting their permutation invariance. This approach makes it highly efficient and effective for a range of applications, including object classification, part segmentation, and scene semantic parsing in 3D. Developed by researchers at Stanford University, PointNet is available as an open-source project on GitHub, providing code and data for training classification and part segmentation networks. It has also served as a foundational work for subsequent advancements like PointNet++.

practical-nlp-code is the official GitHub repository for the code accompanying the 'Practical Natural Language Processing' book published by O'Reilly Media. This repository serves as a comprehensive resource for individuals looking to build real-world NLP systems, providing practical code examples and notebooks. It covers various NLP topics across its chapters, including NLP pipelines, text representation, text classification, information extraction, and applications in areas like chatbots, social media, e-commerce, retail, healthcare, finance, and law. The repository is actively maintained, with ongoing development to update notebooks for newer environments like Ubuntu 23 and future migration to TensorFlow 2.x, making it a valuable learning and development tool for those interested in natural language processing.

The Alexa-Smart Voice Command app for Android is a personal digital voice assistant designed to streamline daily life. With simple voice commands, users can manage tasks, control smart home devices, and receive instant assistance. The app integrates seamlessly with Siri, enhancing its versatility for voice control. It aims to eliminate the hassle of multitasking by allowing users to set reminders, translate voice to text, and stay organized effortlessly. This tool addresses the common problem of overwhelming tasks by providing a convenient and efficient way to manage daily activities.

pysentimiento is an open-source Python toolkit designed for Sentiment Analysis and Social NLP tasks, leveraging Transformer-based models. It offers robust capabilities for sentiment analysis, hate speech detection, irony detection, and emotion analysis across multiple languages including Spanish, English, Italian, and Portuguese. Additionally, it provides NER & POS tagging for Spanish and English, and specialized contextualized hate speech detection and targeted sentiment analysis for Spanish. The library includes a tweet preprocessor optimized for transformer-based models, handling user handles, URLs, repeated characters, laughters, hashtags, and emojis. Developers can easily integrate it into their projects via pip install and utilize its `create_analyzer` function for various tasks.

gpt-go is a simple GPT implementation built from scratch in pure Go, designed for educational purposes and experimentation with AI models. The tool is trained on Jules Verne books and offers a clear, explained codebase for understanding how a GPT model works. It provides instructions on how to run and train the model, including details on dataset customization and chat-only mode. The project emphasizes radical simplicity over maximum efficiency, avoiding complex features like batch processing and external dependencies like gonum to make the underlying mechanics more accessible. It serves as an excellent companion for those following the Neural Networks: Zero to Hero course, with git tags illustrating the model's evolution from naive to full implementation.

GPT4All is an open-source project that enables users to run large language models (LLMs) locally on their everyday desktops and laptops. It eliminates the need for API calls or powerful GPUs, making advanced AI capabilities accessible to a broader audience. The platform supports various model architectures, including DeepSeek R1 Distillations, and offers a Python client for easy integration. Key features include a redesigned chat application UI, improved user workflow for LocalDocs, and support for local LLM inference on NVIDIA and AMD GPUs. GPT4All also provides a Docker-based API server for integrating local LLMs via an OpenAI-compatible HTTP endpoint, fostering private and local data interaction.

gpt-macro is a Rust procedural macro that leverages ChatGPT to generate code during the compilation process. Developers can use natural language prompts within their Rust code to instruct ChatGPT to fill in incomplete functions or generate test cases. This tool streamlines development by automating repetitive coding tasks and enabling rapid prototyping. It integrates directly into the Rust build system, parsing prompts and target code, then replacing the target with code extracted from ChatGPT's response. This allows the Rust compiler to continue with the generated code, making it a powerful assistant for Rust developers.

gpt-migrate is an AI-powered tool designed to streamline the complex and often tedious process of migrating codebases from one framework or language to another. It leverages large language models, preferably GPT-4-32k, to recursively evaluate existing code, identify third-party dependencies, and rebuild new code in the target language. The tool also creates a Docker environment for the target language, develops unit tests, and iteratively debugs the migrated code with context from logs and error messages. While currently in alpha, it aims to significantly reduce the manual effort and costs associated with codebase migrations, offering options for customizing migration behavior and supporting various source and target languages.

GraphEmbedding is a comprehensive open-source Python library designed for the implementation and experimentation of various graph embedding algorithms. It provides ready-to-use implementations of popular algorithms such as DeepWalk, LINE, Node2Vec, SDNE, and Struc2Vec. The library simplifies the process of converting graph structures into vector representations, making them suitable for machine learning models. Users can easily load graph data, initialize models with specific parameters, train them, and retrieve the resulting embeddings. This tool is ideal for researchers and developers working with graph-structured data who need to explore different embedding techniques or integrate graph embeddings into their AI/ML pipelines.

gobrain is an open-source library written in Go, offering fundamental neural network functionalities. It currently supports Feed Forward and Elman Recurrent Neural Networks, allowing developers to construct and train neural networks within the Go programming environment. The library provides methods for initializing network structures, training with specified patterns, and testing the network's performance. It also includes features for persistence, enabling users to save and load trained networks from files. This makes gobrain a suitable choice for developers and data scientists looking to implement and experiment with basic neural network models in Go for various machine learning and AI development tasks.

Rulebook-AI is a command-line tool designed to elevate 'vibe coding' to 'vibe engineering' by providing a universal, managed template for AI coding assistants. It addresses the problem of generic and isolated AI assistants by allowing users to package and deploy consistent expert environments, including rules, context, and helper tools. This ensures long-term memory of project specifics and consistency across different AI tools like Cursor, Gemini, and GitHub Copilot. The tool promotes deep specialization for tasks, composable and versionable contexts, and community-driven expertise through shareable 'Packs'. It supports adding packs from GitHub repos or local filesystems, offering total control over sources and a clean, predictable workspace.

gpt-5-coding-examples is a repository featuring a curated collection of demo applications, all generated entirely from single GPT-5 or GPT-5.2 prompts without any manual coding. This tool highlights the advanced coding capabilities of OpenAI's GPT-5 model, particularly its efficiency in scaffolding websites, front-end applications, games, and interactive user interfaces directly from natural-language descriptions. It serves as an inspirational resource for developers and non-developers alike to explore and build their own ideas. Users can run these examples locally, view the zero-shot prompts used, and adapt them for custom projects. The repository also guides on using GPT-5 with tools like Codex CLI for developers and ChatGPT for non-developers, enabling rapid application development and prototyping.

Whattocode is an AI-powered platform specifically designed to generate frontend coding challenges. This tool aims to provide developers and coding students with a consistent and effective way to practice and improve their frontend development skills. By offering tailored exercises, Whattocode helps users enhance their abilities in various frontend technologies and concepts. The platform focuses on practical application, allowing users to engage with real-world coding scenarios to solidify their understanding and proficiency. It serves as a valuable resource for anyone looking to maintain or advance their frontend coding expertise through regular, targeted practice.

gpt-code-ui is an open-source project that replicates the functionality of OpenAI's ChatGPT Code interpreter, enabling users to interact with AI models to generate and execute code. Users can simply provide natural language prompts, and the tool will generate the corresponding code and run it within its environment. Key features include file upload and download capabilities, context awareness to remember previous messages, and the ability to switch between GPT-3.5 and GPT-4 models. It supports using a .env file for OpenAI API key configuration and offers configurable variables for API and web ports, as well as OpenAI base URL. The tool is designed to simplify coding tasks by automating code generation and execution based on user input, making it a valuable resource for developers looking to leverage AI in their workflows.

PixelVibe is an AI-powered platform designed to create high-quality game assets directly within a web browser. It significantly reduces development time and effort by leveraging generative AI to produce visual elements for games. The tool empowers game developers and creators to efficiently generate diverse assets, making the process of populating game worlds with unique content much faster and more accessible. Its browser-based nature ensures ease of access and use, allowing for asset creation without the need for specialized software installations.

EnhanceAI provides an AI autocomplete solution that integrates GPT-powered functionality into any website with just two lines of code. It allows users to enhance forms, surveys, and text inputs, improving the overall user experience. The tool supports all major no-code tools and UI frameworks, offering flexible and intelligent AI that understands context. EnhanceAI integrates with OpenAI's models, including GPT-3.5 and GPT-4, and offers a free tier for the first 100K tokens. Users can provide custom prompts, control model speed, and view usage analytics, making it a versatile solution for developers and businesses looking to quickly embed AI capabilities.

Harbor is a robust, open-source framework designed for the evaluation and optimization of AI agents and language models. Developed by the creators of Terminal-Bench, it provides a comprehensive toolkit for assessing agent performance, including those like Claude Code and OpenHands. Users can leverage Harbor to create and share custom benchmarks and environments, facilitating diverse experimental setups. The framework supports parallel execution of experiments across thousands of environments, utilizing providers such as Daytona and Modal, and can generate rollouts for reinforcement learning optimization. Its flexibility makes it suitable for a wide range of AI development and research tasks.